Navigation planning method and system based on detailed terrain information and vehicle characteristics

By integrating drones, vehicle cameras and sensors, collecting and analyzing terrain and meteorological information in real time, combining vehicle performance parameters, and applying path planning algorithms to generate customized navigation solutions, the existing navigation system's navigation accuracy and safety in harsh environments is solved. The problem of insufficient achieves more efficient and secure navigation.

CN119085686APending Publication Date: 2024-12-06DONGFENG OFF ROAD VEHICLE CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411294099.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing navigation systems cannot effectively provide customized navigation solutions for special off-road vehicles in complex and harsh environments, especially under rapidly changing terrain and road conditions, which makes traditional navigation systems difficult to ensure navigation accuracy and safety.

Method used

By integrating drones, vehicle cameras, sensors and other equipment, we collect and analyze terrain, meteorological and road conditions information in real time, and use external data interface modules to obtain the latest information. Combined with vehicle performance parameters, we use path planning algorithms to generate highly customized navigation solutions. , establish feasibility and risk scoring models, and generate the optimal navigation path.

Benefits of technology

Significantly improves the navigation accuracy and safety of special off-road vehicles in complex and harsh environments, provides optimized navigation suggestions, reduces completion time of rescue or special tasks, reduces associated risks, and improves the flexibility and adaptability of navigation systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085686A_ABST
    Figure CN119085686A_ABST
Patent Text Reader

Abstract

The invention discloses a navigation planning method and system based on detailed terrain information and vehicle characteristics. The method comprises the following steps: acquiring latest terrain, weather and road condition information in real time; carrying out data preprocessing on the vehicle performance parameters and the terrain, weather and road condition information; extracting a topographic feature vector and a meteorological feature vector from the preprocessed topographic and meteorological information; calculating the driving feasibility of the vehicle on the specific terrain by using the vehicle performance parameters and the terrain feature vectors, and establishing an evaluation model; and calculating the driving risk degree of the vehicle under the specific terrain and weather conditions by using the vehicle performance parameters and the terrain and weather feature vectors, and establishing a risk model. And on the basis of the evaluation model and the risk model in the step S300, generating one or more possible navigation routes by applying a path planning algorithm to generate an optimal or more alternative navigation paths. The navigation precision and safety of the special off-road vehicle in a complex and severe environment are remarkably improved, and related risks are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle navigation, and in particular to a navigation planning method and system based on detailed terrain information and vehicle characteristics. Background Art

[0002] Modern vehicle navigation systems rely mainly on huge road network data for route planning and navigation. These data are usually based on the road conditions that ordinary passenger cars or trucks can pass, such as highways, city streets, rural roads, etc. Such road network data is relatively effective and suitable for most occasions and vehicle types. However, this universal navigation logic and data model cannot meet some special needs and application scenarios. Special off-road vehicles, such as emergency rescue vehicles, military vehicles, and forestry vehicles, often need to operate in unconventional and harsh environments. These environments may include rugged and steep mountain roads, muddy ground, deserts, ice and snow covered areas, etc. In such environments, traditional road network data obviously cannot provide suitable and effective navigation solutions. Special off-road vehicles usually have higher ground clearance, stronger climbing ability, and better off-road performance, which enables them to traverse many areas that traditional navigation systems consider inaccessible.

[0003] There are some navigation systems designed for off-road vehicles or special environments in the prior art, including offline map navigation and online off-road navigation. Off-line navigation systems usually include a set of pre-downloaded terrain map data and some basic off-road navigation functions, which provide users with the ability to perform basic navigation without a network connection. Online off-road navigation applications allow users to upload and share their own off-road experiences and routes. These applications usually have social networking functions that allow users to rate, mark and share specific off-road routes.

[0004] However, both solutions have obvious limitations. Offline terrain map navigation systems cannot update terrain or road conditions in real time, which means that they may become inaccurate or even dangerous when dealing with rapidly changing environments (such as floods or mudslides). Existing online off-road navigation, firstly, because the information comes from online users, the data quality and accuracy may not be guaranteed; secondly, such applications usually lack the ability to quantify vehicle performance parameters and terrain data, making it difficult to provide customized services for special off-road vehicles of different types and specifications. And these systems are usually based on experience or pre-entered terrain data, rather than real-time or highly customized navigation solutions. They often cannot perform detailed route planning based on the specific parameters of the vehicle (such as length, width, height, climbing ability, wading ability, etc.). Summary of the invention

[0005] In view of the above defects or improvement needs of the prior art, the purpose of the present invention is to provide a navigation planning method and system based on detailed terrain information and vehicle characteristics, which can collect and analyze terrain, weather and road condition information in real time by integrating drones, vehicle cameras, sensors and other equipment, and obtain current terrain, weather and road condition information from multiple data suppliers or other reliable sources through an external data interface module; at the same time, using a database storage module, the system can store and manage various performance parameters of special off-road vehicles; then, through the real-time analysis engine module, the specific parameters of the vehicle, such as length, width, height, climbing ability, wading ability, etc., can be matched and analyzed with the collected terrain information, and a path planning algorithm can be used to generate a highly customized navigation solution, which significantly improves the navigation accuracy and safety of special off-road vehicles in complex and harsh environments.

[0006] To achieve this object, according to a first aspect of the present invention, a navigation planning method based on detailed terrain information and vehicle characteristics is provided, comprising:

[0007] S100, acquiring the latest terrain information and weather information in real time; and performing data preprocessing on vehicle performance parameters and the terrain information and weather information;

[0008] S200, extracting a terrain feature vector and a meteorological feature vector from the preprocessed terrain information and meteorological information;

[0009] S300, using vehicle performance parameters and terrain feature vectors, calculating the feasibility of the vehicle traveling on a specific terrain, and establishing an evaluation model; using vehicle performance parameters, terrain feature vectors, and meteorological feature vectors, calculating the risk level of the vehicle traveling under specific terrain and meteorological conditions, and establishing a risk model.

[0010] S400, based on the evaluation model and risk model in step S300, each possible section or plot is regarded as a node, and the path planning algorithm is applied to calculate the total cost of the current node and all other nodes, and one or more possible navigation routes are generated according to the analysis results to generate the optimal or multiple alternative navigation paths, and sort them according to the predefined evaluation criteria combined with the input task type.

[0011] Furthermore, step S100 includes: collecting the latest terrain, weather and road condition information in real time through vehicle-mounted cameras, sensors and drones, and continuously communicating with data providers or other reliable sources to obtain the latest terrain, weather and road condition information.

[0012] Furthermore, the data preprocessing in step S200 includes missing value processing, outlier detection, unit conversion, feature encoding and data scaling.

[0013] Furthermore, the establishment of the evaluation model in step S300 includes:

[0014] S301. Calculate the slope feasibility coefficient F slope ; Terrain complexity feasibility coefficient F terrain ; Water wading feasibility coefficient F water ;

[0015]

[0016] In the formula, θ max represents the maximum climbing grade; θ represents the slope; D max Indicates the maximum wading depth; D indicates the slope;

[0017] S302, setting weights for various vehicle performance parameters according to their influence;

[0018] S303. Calculate the comprehensive feasibility score F total

[0019] F total =ω1×F slope +ω2×F terrain +ω3×F water +…

[0020] In the formula, ω1, ω2, ω3, ... represent the feasibility weight coefficients of each parameter, and the sum of all weight coefficients is 1.

[0021] Further, step S400 includes:

[0022] S401, treating each possible section or plot as a node, and setting the path starting point as the current node;

[0023] S402, calculate the actual cost g(n) from the starting point to the current node:

[0024]

[0025] Where D(n) represents the actual distance from the starting point to the node; S(n) represents the comprehensive score of the path from the starting point to the node; ∈ is a small constant used to avoid the denominator being zero; α and β represent weight parameters, which determine the relative importance of distance and score in cost calculation.

[0026] Further, including:

[0027] S403, calculate the estimated cost h(n) from the current node to the target:

[0028]

[0029] Where d(n) is the Euclidean distance from the current node to the target node; s avgis the average comprehensive score on the known path; γ is a weight coefficient that can adjust the relative importance between Euclidean distance and comprehensive score;

[0030] S404: Calculate the total cost f(n)=g(n)+h(n).

[0031] Further, step S400 includes:

[0032] S405. For the current node, consider all nodes that can be directly reached from the current node as neighbor nodes; for each neighbor node, calculate the cost g(n′) from the starting point through the current node to the neighbor node, and the estimated cost h(n′) from the neighbor node to the end point;

[0033] S406, calculate the total cost f(n′)=g(n′)+h(n′); select the node with the lowest f(n′) value from the nodes that have not been visited as the next current node;

[0034] Further, it includes: repeating steps S405 and S406 until the end point is reached or all possible paths have been considered; starting from the end point, backtracking through the parent node of each node until returning to the starting point.

[0035] Further, including:

[0036] During the navigation process, the system will continuously receive new terrain, weather and road conditions information, recalculate the path planning, and make necessary real-time adjustments.

[0037] According to a second aspect of the present invention, a navigation planning system based on detailed terrain information and vehicle characteristics is provided, which is implemented by applying any step in the above-mentioned navigation planning method based on detailed terrain information and vehicle characteristics, including:

[0038] UAV deployment module for obtaining high-quality real-time terrain and road condition information;

[0039] Vehicle camera module, used to obtain close-range terrain information and road condition information in real time;

[0040] The sensor module is used to locate the current position and obtain the current terrain and weather information in real time;

[0041] External data interface module: used to obtain current terrain, weather and road condition information from multiple data suppliers or other reliable sources;

[0042] Data integration and analysis module, which is used to receive, process and integrate the information obtained from various modules, perform data integration and analysis, and provide preliminary road condition and environmental assessment;

[0043] A data storage module, used to store data output by the data integration and analysis module;

[0044] A real-time analysis engine module is used to use vehicle performance parameters and terrain feature vectors to calculate the feasibility of a vehicle traveling on a specific terrain and establish an evaluation model; use vehicle performance parameters, terrain and meteorological feature vectors to calculate the risk level of a vehicle traveling under specific terrain and meteorological conditions and establish a risk model; based on the evaluation model and risk model, a path planning algorithm is applied to calculate the total cost of the current node and all other nodes, and the analysis results are output;

[0045] The navigation generation module is used to generate one or more navigation routes for specific vehicles and tasks based on the output of the real-time analysis engine module, and sort them according to predefined evaluation criteria combined with input task types.

[0046] Beneficial effects of the present invention:

[0047] 1. The present invention provides a navigation planning system based on detailed terrain information and vehicle characteristics. By integrating unmanned aerial vehicles, vehicle cameras, sensors and other equipment, the system collects and analyzes terrain, weather and road condition information in real time, and obtains current terrain, weather and road condition information from multiple data suppliers or other reliable sources through an external data interface module. At the same time, by using a database storage module, the system can store and manage various performance parameters of special off-road vehicles. Then, through a real-time analysis engine module, the specific parameters of the vehicle, such as length, width, height, climbing ability, wading ability, etc., can be matched and analyzed with the collected terrain information, and a path planning algorithm is applied to generate a highly customized navigation solution. This method significantly improves the navigation accuracy and safety of special off-road vehicles in complex and harsh environments.

[0048] 2. The present invention provides a navigation planning method based on detailed terrain information and vehicle characteristics, which uses an advanced A* path planning algorithm and combines feasibility and risk scoring models to provide optimized navigation suggestions for special off-road vehicles under specific environmental conditions. By comprehensively evaluating factors such as terrain, meteorological conditions, and vehicle performance parameters, the system can generate one or more optimal paths for specific vehicles and tasks. This optimized path planning algorithm can not only help quickly find the safest path, but also reduce the completion time of rescue or other special tasks and reduce related risks.

[0049] 3. The navigation planning system based on detailed terrain information and vehicle characteristics provided by the present invention can be applied to other scenarios requiring special off-road vehicles, such as field operations, military operations, etc., in addition to playing a role in disaster relief. The system uses the real-time navigation function to enable the vehicle to continuously receive and process new data during the navigation process in order to make necessary route adjustments, thereby improving flexibility and adaptability in different application scenarios.

[0050] Additional aspects and advantages of the present application will be partially given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0052] Figure 1 is a flow chart of a navigation planning method based on detailed terrain information and vehicle characteristics in an embodiment of the present invention;

[0053] Figure 2 This is a flow chart of step S300 in a navigation planning method based on detailed terrain information and vehicle characteristics in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0055] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0056] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and will not be interpreted with an idealized or overly formal meaning unless specifically defined as in the embodiments of this application.

[0057] The present invention provides a navigation planning method and system based on detailed terrain information and vehicle characteristics. By integrating unmanned aerial vehicles, vehicle cameras, sensors and other equipment, the method and system can collect and analyze terrain, weather and road condition information in real time, and obtain current terrain, weather and road condition information from multiple data suppliers or other reliable sources through an external data interface module. At the same time, by using a database storage module, the system can store and manage various performance parameters of special off-road vehicles. Then, through a real-time analysis engine module, the specific parameters of the vehicle, such as length, width, height, climbing ability, wading ability, etc., can be matched and analyzed with the collected terrain information, and a path planning algorithm can be used to generate a highly customized navigation solution, which significantly improves the navigation accuracy and safety of special off-road vehicles in complex and harsh environments.

[0058] Embodiment 1:

[0059] like Figure 1 As shown, an embodiment of the present invention provides a navigation planning method based on detailed terrain information and vehicle characteristics, which is applied to an off-road vehicle onboard system, including:

[0060] S100, acquiring the latest terrain, weather and road condition information in real time; and performing data preprocessing on vehicle performance parameters and the terrain, weather and road condition information;

[0061] Deploy drones equipped with high-resolution cameras and radar scanning equipment on off-road vehicles to obtain high-quality real-time terrain and road conditions information; use vehicle-mounted cameras fixed on vehicles at different angles to obtain close-range road conditions and environmental data in real time; use vehicle-mounted sensors, including GPS sensors, climate sensors (temperature, humidity, wind speed, etc.) and terrain recognition sensors (such as ground hardness, slope, etc.) to obtain the vehicle's current location, current weather information and terrain information; use external data interface modules to obtain multi-dimensional information such as terrain, weather and road conditions from multiple data suppliers or other reliable sources; pre-process various collected data (including vehicle performance parameters, terrain data, meteorological data, etc.), clean up unnecessary or erroneous data, and standardize the data to ensure that the data units and scales are consistent, including:

[0062] 1. Missing value processing: fill missing values ​​by interpolation or using neighboring data;

[0063] 2. Outlier detection: Identify and handle outliers, possibly replacing or correcting them through the mean, median, or other statistical methods;

[0064] 3. Unit conversion: If the data source provides data in different units, you need to apply the corresponding conversion formula to unify them into the same unit. (For example, temperature may have two units, Celsius and Fahrenheit, and approach angle and departure angle may have units of degrees or radians);

[0065] 4. Feature encoding: For non-numerical (such as categorical or text data) features (such as flat, slope, steep slope), one-hot encoding may be required to convert them into numerical form;

[0066] 5. Data scaling: adjust the value to between 0 and 1 through the maximum-minimum normalization method;

[0067] S200, extracting a terrain feature vector and a meteorological feature vector from the preprocessed terrain and meteorological information;

[0068] S300, using vehicle performance parameters and terrain feature vectors, calculating the feasibility of the vehicle traveling on a specific terrain, and establishing an evaluation model; using vehicle performance parameters, terrain and meteorological feature vectors, calculating the risk level of the vehicle traveling under specific terrain and meteorological conditions, and establishing a risk model.

[0069] like Figure 2 As shown, step S300 specifically includes:

[0070] S301. Calculate the slope feasibility coefficient F slope ; Terrain complexity feasibility coefficient F terrain ; Water wading feasibility coefficient F water ;

[0071]

[0072] In the formula, θ max represents the maximum climbing grade; θ represents the slope; D max Indicates the maximum wading depth; D indicates the slope;

[0073] S302, setting weights for various vehicle performance parameters according to their influence;

[0074] S303. Calculate the comprehensive feasibility score F total :

[0075] F total =ω1×F slope +ω2×F terrain +ω3×F water +…

[0076] In the formula, ω1, ω2, ω3, ... represent the feasibility weight coefficients of each parameter, and the sum of all weight coefficients is 1.

[0077] S400, based on the evaluation model and risk model in step S300, each possible section or plot is regarded as a node, and the path planning algorithm is applied to calculate the total cost of the current node and all other nodes, and one or more possible navigation routes are generated according to the analysis results to generate the optimal or multiple alternative navigation paths, and sort them according to the predefined evaluation criteria combined with the input task type.

[0078] This embodiment uses the A* algorithm for path planning. In the A* algorithm, the total cost of each node is usually composed of two parts: one is the actual cost from the starting point to the current node (usually referred to as g(n)), and the other is the estimated cost from the current node to the target (heuristic function, usually referred to as h(n)). The total cost is expressed as f(n), which is calculated as follows: f(n) = g(n) + h(n). Each section of road or plot is evaluated using the feasibility and risk scoring model mentioned above. This model takes into account terrain, weather and vehicle parameters to generate a feasibility and risk score, which reflects the actual cost of the vehicle traveling on the section of road or plot. While considering feasibility and risk, the actual distance of the path also needs to be considered. The distance parameter is integrated with the feasibility and risk score to design a cost function: The purpose of the heuristic function h(n) is to estimate the cost of the best path from the current node to the target node. A commonly used heuristic function is based on the Euclidean distance (the straight-line distance between two points), but in this system, using only the Euclidean distance may not be accurate enough. Therefore, we designed a heuristic function that combines the Euclidean distance with a comprehensive score of feasibility and risk; specifically:

[0079] S401, treating each possible section or plot as a node, and setting the path starting point as the current node;

[0080] S402, calculate the actual cost g(n) from the starting point to the current node:

[0081]

[0082] Where D(n) represents the actual distance from the starting point to the node; S(n) represents the comprehensive score of the path from the starting point to the node; ∈ is a small constant used to avoid the denominator being zero; α and β represent weight parameters, which determine the relative importance of distance and score in cost calculation.

[0083] In this model, when the comprehensive score S(n) increases, the cost decreases; when the comprehensive score S(n) decreases, the cost increases. At the same time, this model can achieve different preferences for path distance and comprehensive score by adjusting the values ​​of α and β. For example, if you want to emphasize paths with shorter distances, you can increase the value of α; if you want to emphasize paths with high feasibility and low risk, you can increase the value of β.

[0084] S403, calculate the estimated cost h(n) from the current node to the target:

[0085]

[0086] Where d(n) is the Euclidean distance from the current node to the target node; s avg is the average comprehensive score on the known path; γ is a weight coefficient that can adjust the relative importance between Euclidean distance and comprehensive score;

[0087] S404: Calculate the total cost f(n)=g(n)+h(n).

[0088] S405. For the current node, consider all nodes that can be directly reached from the current node as neighbor nodes; for each neighbor node, calculate the cost g(n′) from the starting point through the current node to the neighbor node, and the estimated cost h(n′) from the neighbor node to the end point;

[0089] S406, calculate the total cost f(n′)=g(n′)+h(n′); select the node with the lowest f(n′) value from the nodes that have not been visited as the next current node;

[0090] Further, steps S405 and S406 are repeated until the end point is reached or all possible paths have been considered; starting from the end point, backtrack through the parent node of each node until returning to the starting point.

[0091] In summary, the embodiment of the present invention provides a navigation planning method based on detailed terrain information and vehicle characteristics, which adopts an advanced A* path planning algorithm and combines feasibility and risk scoring models to provide optimized navigation suggestions for special off-road vehicles under specific environmental conditions. By comprehensively evaluating factors such as terrain, meteorological conditions, and vehicle performance parameters, the system can generate one or more optimal paths for specific vehicles and tasks. This optimized path planning algorithm can not only help quickly find the safest path, but also reduce the completion time of rescue or other special tasks and reduce related risks.

[0092] Embodiment 2:

[0093] The embodiment of the present invention provides a navigation planning system based on detailed terrain information and vehicle characteristics, which is implemented by applying any step in a navigation planning method based on detailed terrain information and vehicle characteristics in Embodiment 1, including:

[0094] UAV deployment module for obtaining high-quality real-time terrain and road condition information;

[0095] Vehicle camera module, used to obtain close-range terrain information and road condition information in real time;

[0096] The sensor module is used to locate the current position and obtain the current terrain and weather information in real time;

[0097] External data interface module: used to obtain current terrain, weather and road condition information from multiple data suppliers or other reliable sources;

[0098] Data integration and analysis module, which is used to receive, process and integrate the information obtained from various modules, perform data integration and analysis, and provide preliminary road condition and environmental assessment;

[0099] A data storage module, used to store data output by the data integration and analysis module;

[0100] A real-time analysis engine module is used to use vehicle performance parameters and terrain feature vectors to calculate the feasibility of a vehicle traveling on a specific terrain and establish an evaluation model; use vehicle performance parameters, terrain and meteorological feature vectors to calculate the risk level of a vehicle traveling under specific terrain and meteorological conditions and establish a risk model; based on the evaluation model and risk model, a path planning algorithm is applied to calculate the total cost of the current node and all other nodes, and the analysis results are output;

[0101] The navigation generation module is used to generate one or more navigation routes for specific vehicles and tasks based on the output of the real-time analysis engine module, and sort them according to predefined evaluation criteria combined with input task types.

[0102] After the navigation route is generated, the system can display the generated navigation route through the user interface and wait for the user to confirm. Once the user confirms, the system will start real-time navigation. During the navigation process, the system will continue to receive new terrain, weather and road conditions information, recalculate the path planning, and make necessary real-time adjustments.

[0103] Before the system starts working, the user needs to input the specific mission type (such as emergency rescue, disaster relief, etc.) and destination through the user interface, and the data acquisition subsystem enters the pre-mission preparation stage. Before the mission begins, the drone first conducts a pre-flight to scan the planned route and its surrounding terrain, and the data is transmitted back to the data integration and analysis module in real time. The on-board camera and sensor perform functional self-tests to ensure that all equipment is in working condition.

[0104] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0105] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A navigation planning method based on detailed terrain information and vehicle characteristics, characterized in that: include: S100, real-time acquisition of the latest terrain and weather information; and performing data preprocessing on vehicle performance parameters and the terrain information and meteorological information; S200, extracting a terrain feature vector and a meteorological feature vector from the preprocessed terrain information and meteorological information; S300, using vehicle performance parameters and terrain feature vectors, calculating the feasibility of the vehicle traveling on a specific terrain, and establishing an evaluation model; using vehicle performance parameters, terrain feature vectors, and meteorological feature vectors, calculating the risk level of the vehicle traveling under specific terrain and meteorological conditions, and establishing a risk model; S400, based on the evaluation model and risk model in step S300, each possible section or plot is regarded as a node, and the path planning algorithm is applied to calculate the total cost of the current node and all other nodes, and one or more possible navigation routes are generated according to the analysis results to generate the optimal or multiple alternative navigation paths, and sort them according to the predefined evaluation criteria combined with the input task type.

2. A navigation planning method based on detailed terrain information and vehicle characteristics according to claim 1, characterized in that: Step S100 includes: collecting the latest terrain, weather and road condition information in real time through vehicle-mounted cameras, sensors and drones, and continuously communicating with data providers or other reliable sources to obtain the latest terrain, weather and road condition information.

3. A navigation planning method based on detailed terrain information and vehicle characteristics according to claim 1, characterized in that: The data preprocessing in step S200 includes missing value processing, outlier detection, unit conversion, feature encoding and data scaling.

4. A navigation planning method based on detailed terrain information and vehicle characteristics according to claim 1, characterized in that: The step S300 of establishing the evaluation model includes: S301. Calculate the slope feasibility coefficient F slope ; Terrain complexity feasibility coefficient F terrain ; Water wading feasibility coefficient F water ; In the formula, θ max represents the maximum climbing grade; θ represents the slope; D max Indicates the maximum wading depth; D indicates the slope; S302, setting weights for various vehicle performance parameters according to their influence; S303. Calculate the comprehensive feasibility score F total F total =ω1×F slope +ω2×F terrain +ω3×F water +… In the formula, ω1, ω2, ω3, ... represent the feasibility weight coefficients of each parameter, and the sum of all weight coefficients is 1.

5. The navigation planning method based on detailed terrain information and vehicle characteristics according to claim 1, characterized in that: Step S400 includes: S401, treating each possible section or plot as a node, and setting the path starting point as the current node; S402, calculate the actual cost g(n) from the starting point to the current node: Where D(n) represents the actual distance from the starting point to the node; S(n) represents the comprehensive score of the path from the starting point to the node; ∈ is a small constant used to avoid the denominator being zero; α and β represent weight parameters, which determine the relative importance of distance and score in cost calculation.

6. A navigation planning method based on detailed terrain information and vehicle characteristics according to claim 5, characterized in that: include: S403, calculate the estimated cost h(n) from the current node to the target: Where d(n) is the Euclidean distance from the current node to the target node; s avg is the average comprehensive score on the known paths; γ is a weight coefficient that adjusts the relative importance between the Euclidean distance and the comprehensive score; S404: Calculate the total cost f(n)=g(n)+h(n).

7. A navigation planning method based on detailed terrain information and vehicle characteristics according to claim 6, characterized in that: Step S400 includes: S405. For the current node, consider all nodes that can be directly reached from the current node as neighbor nodes; for each neighbor node, calculate the cost g(n′) from the starting point through the current node to the neighbor node, and the estimated cost h(n′) from the neighbor node to the end point; S406, calculate the total cost f(n′)=g(n′)+h(n′); select the node with the lowest f(n′) value from the unvisited nodes as the next current node.

8. A navigation planning method based on detailed terrain information and vehicle characteristics according to claim 7, characterized in that: include: Repeat steps S405 and S406 until the end point is reached or all possible paths have been considered; Start at the end point and backtrack through the parent node of each node until you get back to the starting point.

9. A navigation planning method based on detailed terrain information and vehicle characteristics according to any one of claims 1 to 8, characterized in that: include: During the navigation process, the system will continuously receive new terrain, weather and road conditions information, recalculate the path planning, and make necessary real-time adjustments.

10. A navigation planning system based on detailed terrain information and vehicle characteristics, implemented by using a navigation planning method based on detailed terrain information and vehicle characteristics as claimed in any one of claims 1 to 9, characterized in that: include: UAV deployment module for obtaining high-quality real-time terrain and road condition information; Vehicle camera module, used to obtain close-range terrain information and road condition information in real time; The sensor module is used to locate the current position and obtain the current terrain and weather information in real time; External data interface module: used to obtain current terrain, weather and road condition information from multiple data suppliers or other reliable sources; Data integration and analysis module, which is used to receive, process and integrate the information obtained from various modules, perform data integration and analysis, and provide preliminary road condition and environmental assessment; A data storage module, used to store data output by the data integration and analysis module; A real-time analysis engine module is used to use vehicle performance parameters and terrain feature vectors to calculate the feasibility of a vehicle traveling on a specific terrain and establish an evaluation model; use vehicle performance parameters, terrain and meteorological feature vectors to calculate the risk level of a vehicle traveling under specific terrain and meteorological conditions and establish a risk model; based on the evaluation model and risk model, a path planning algorithm is applied to calculate the total cost of the current node and all other nodes, and the analysis results are output; The navigation generation module is used to generate one or more navigation routes for specific vehicles and tasks based on the output of the real-time analysis engine module, and sort them according to predefined evaluation criteria combined with input task types.

Citation Information

Cited By

  • DOP information fused long-distance maneuvering path planning method and system

    CN121475263A